Home	People	Research	Publications	Demos
News	Jobs	Prospective Students	About	Internal

Antoni B. Chan Department of Electrical and Computer Engineering, University of California, San Diego 9500 Gilman Drive, Mail code 0409 La Jolla, CA 92093-0409 EBU 1, Room 5512 abchan at u c s d . e d u Phone: (858) 534-4538 Fax: (858) 534-1225 CV: pdf

I am currently a PhD student in the Statistical Visual Computing Lab (SVCL) of the Electrical and Computer Engineering Department at the University of California, San Diego. I received my B.S. and M.Eng. in Electrical Engineering from Cornell University in 2000 and 2001. From 2001 to 2003, I was a Visiting Scientist in the Vision and Image Analysis lab at Cornell, and in 2005, I had a summer internship at Google in New York City.
Research:
	My research interests are computer vision and machine learning, and more specifically, the application of probablistic models to classification and retrieval of images and video. My current research is directed at modeling motion in video using stochastic processes (e.g. dynamic textures and its extensions). These models can be applied to a wide array of computer vision problems, e.g. video retrieval, video clustering, video synthesis, and motion segmentation. I am interested in image and video classification using support vector machines and probabilistic kernels. In particular, I am looking at probabilistic kernel theory and the efficient approximations of these kernels. I am also interested in image annotation and retrieval.
Main Research Topics:
	Dynamic Textures A family of generative stochastic dynamic texture models for analyzing motion. [project] Understanding Video of Crowded Environments Motion segmentation and motion classification in video of crowded environments, such as pedestrian scenes and highway traffic. [project]
Projects:
	Pedestrian Crowd Counting new! We estimate the size of moving crowds in a privacy preserving manner, i.e. without people models or tracking. The system first segments the crowd by its motion, extracts low-level features from each segment, and estimates the crowd count in each segment using a Gaussian process. [project | demo] Kernel Dynamic Textures We introduce a kernelized dynamic texture, which has a non-linear observation function learned with kernel PCA. The new texture model can account for more complex patterns of motion, such as chaotic motion (e.g. boiling water and fire) and camera motion (e.g. panning and zooming), better than the original dynamic texture. [demo coming soon] Classification and Retrieval of Traffic Video We classify traffic congestion in video by representing the video as a dynamic texture, and classifying it using an SVM with a probabilistic kernel (the KL kernel). The resulting classifier is robust to noise and lighting changes. [project | demo] Modeling video with Mixtures of Dynamic Textures We introduce the mixture of dynamic textures, which models a collection of video as samples from a set of dynamic textures. We use the model for video clustering and motion segmentation. [project | demo] Layered Dynamic Textures One disadvantage of the dynamic texture is its inability to account for multiple co-occuring textures in a single video. We extend the dynamic texture to a multi-state (layered) dynamic texture that can learn regions containing different dynamic textures. [demo] Semantic Image Annotation and Retrieval We annotate images using supervised multi-class labeling (SML), which treats semantic annotation as a multi-class classification problem. The system is scalable, and was applied to image databases with 60,000 images. [project | annotation and retrieval demos] [SML for audio annotation and retrieval]
Publications:
	Privacy Preserving Crowd Monitoring: Counting People without People Models or Tracking A. B. Chan, Z. S. J. Liang, and N. Vasconcelos. In, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2008. © IEEE [ps][pdf] Modeling, clustering, and segmenting video with mixtures of dynamic textures A. B. Chan and N. Vasconcelos. IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 30(5), pp. 909-926, May 2008. © IEEE [ps][pdf] Classifying Video with Kernel Dynamic Textures A. B. Chan and N. Vasconcelos Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, June 2007. [ps][pdf] Direct Convex Relaxations of Sparse SVM A. B. Chan, N. Vasconcelos, and G. R. G. Lanckriet Proceedings of International Conference on Machine Learning (ICML), Corvallis, OR, June 2007. [ps][pdf] (updated) (this old version accidently truncated the last dimension of the "wine" dataset [ps][pdf]) Supervised learning of semantic classes for image annotation and retrieval G. Carneiro, A. B. Chan, P. J. Moreno, and N. Vasconcelos. IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 29(3), pp. 394-410, March 2007.© IEEE,[pdf] Audio Information Retrieval using Semantic Similarity L. Barrington, A. B. Chan, D. Turnbull, and G. Lanckriet. Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Honolulu, April 2007 [pdf] Using Statistics to Search and Annotate Pictures: an Evaluation of Semantic Image Annotation and Retrieval on Large Databases A. B. Chan, P. J. Moreno, and N. Vasconcelos. Proceedings of the American Statistical Association, Seattle, August 2006 [ps][pdf] Layered Dynamic Textures A. B. Chan and N. Vasconcelos, Proceedings of Neural Information Processing Systems 18 (NIPS), pp. 203-210, Vancouver, December 2005. [ps][pdf] Mixtures of Dynamic Textures A. B. Chan and N. Vasconcelos, Proceedings of IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 2005. © IEEE, [ps][pdf] Probabilistic Kernels for the Classification of Auto-regressive Visual Processes A. B. Chan and N. Vasconcelos, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, 2005. © IEEE, [ps][pdf] (a longer version is available [ps][pdf]). Classification and Retrieval of Traffic Video using Auto-regressive Stochastic Processes A. B. Chan and N. Vasconcelos, Proceedings of 2005 IEEE Intelligent Vehicles Symposium (IEEEIV), Las Vegas, June 2005. © IEEE, [pdf]. On Measuring the Change in Size of Pulmonary Nodules A. P. Reeves, A. B. Chan, D. F. Yankelevitz, C. I. Henschke, B. Kressler, W. J. Kostis, IEEE Transactions on Medical Imaging (TMI). Vol. 25(4), pp. 435-450, April 2006. © IEEE, [pdf].
Oral Presentations:
	Direct Convex Relaxations of Sparse SVM International Conference on Machine Learning, Corvallis, OR, May 2007. Classification and Clustering of Motion Flow using Dynamic Textures Emerging Leaders in Multimedia Workshop, IBM Watson, October 2006. [slides] Layered Dynamic Textures ICCV Workshop on Dynamical Vision, Beijing, October 2005. [slides] Probabilistic Kernels for the Classification of Auto-regressive Visual Processes IEEE Conference on Computer Vision and Pattern Recognition, San Diego, June 2005. [slides] Classification and Retrieval of Traffic Video using Auto-regressive Stochastic Processes IEEE Intelligent Vehicles Symposium, Las Vegas, June 2005. [slides] A Family of Probabilistic Kernels Based on Information Divergence NIPS Workshop on Graphical Models and Kernels, Whistler, Dec 2004. [slides]
Technical Reports:
	Supplemental for "Classifying Video with Kernel Dynamic Textures" A. B. Chan and N. Vasconcelos. Technical Report SVCL-TR-2007-03, April, 2007. [ps][pdf][zip w/ video] Duals of the QCQP and SDP Sparse SVM A. B. Chan, N. Vasconcelos, and G. R. G. Lanckriet, Technical Report SVCL-TR-2007-02, April 2007. [ps][pdf] The EM Algorithm for Layered Dynamic Textures A. B. Chan and N. Vasconcelos, Technical Report SVCL-TR-2005-03, 2005. [ps][pdf] The EM Algorithm for Mixtures of Dynamic Textures A. B. Chan and N. Vasconcelos, Technical Report SVCL-TR-2005-02, 2005. [ps][pdf] Efficient Computation of the KL Divergence between Dynamic Textures A. B. Chan and N. Vasconcelos, Technical Report SVCL-TR-2004-02, November 2004. [ps][pdf] A Family of Probabilistic Kernels Based on Information Divergence A. B. Chan, N. Vasconcelos, and P. J. Moreno, Technical Report SVCL-TR-2004-01, June 2004. [ps][pdf]
Awards and Honors:
	NSF IGERT Fellowship: Vision and Learning in Humans and Machines, UCSD, 2006-07 Outstanding Teaching Assistant Award, ECE Department, UCSD, 2005-06 Office of the President Award, UCSD, 2003 Henry G. White Scholorship, Cornell University, 2001. Knauss M. Engineering Scholorship, Cornell University, 2001. GTE Fellowship, Cornell University, 2001.
Links:
	NIPS (Neural Information Processing Systems) ICCV 2003 (IEEE Conference on Computer Vision) ECCV 2004 (European Conference on Computer Vision CVPR 2004 (IEEE Conference on Computer Vision and Pattern Recognition) PAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence) IEEE Berkeley Digital Library Project Computational Vision Lab (Caltech) UCLA Vision Lab kernel-machines.org libsvm, very good SVM library Matrix reference MATLAB helpdesk PERL documentation my VIA webpage (Note: some information on this page is out of date)
Other Links:
	Personal Website All Too Flat Cockeyed PhD Comics

Last update: 05/05/2007

Copyright @ 2007 www.svcl.ucsd.edu